java-codebase-rag 0.5.1__tar.gz → 0.5.3__tar.gz

{java_codebase_rag-0.5.1/java_codebase_rag.egg-info → java_codebase_rag-0.5.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: java-codebase-rag
-Version: 0.5.1
+Version: 0.5.3
 Summary: MCP server for semantic + structural search over Java codebases
 Author: HumanBean17
 License-Expression: MIT
@@ -84,6 +84,31 @@ pip install java-codebase-rag
 Python **3.11+** required. After install, `java-codebase-rag --help` should print the CLI groups.
 The package includes the CocoIndex lifecycle dependency used by `init`, `increment`, `reprocess`, and `erase`.
 
+### Interactive setup (recommended)
+
+Run `java-codebase-rag install` from your Java project root to launch an interactive setup wizard that:
+
+1. Detects Java source directories (Maven/Gradle modules)
+2. Configures the embedding model (auto-downloads ~90MB or uses a local path)
+3. Selects agent hosts (Claude Code, Qwen Code, GigaCode)
+4. Deploys MCP registration, skill, and agent artifacts
+5. Generates `.java-codebase-rag.yml` configuration
+6. Runs `init` to build the index
+
+```bash
+# Interactive mode
+java-codebase-rag install
+
+# Non-interactive mode (for CI/automation)
+java-codebase-rag install --non-interactive --agent claude-code
+```
+
+After `pip install --upgrade java-codebase-rag`, run `java-codebase-rag update` to refresh shipped artifacts.
+
+### Manual registration
+
+If you prefer manual configuration, see [`docs/JAVA-CODEBASE-RAG-CLI.md`](./docs/JAVA-CODEBASE-RAG-CLI.md) for the full CLI reference.
+
 > **Stability disclaimer.** This package does **not** promise backward compatibility. MCP tool contracts, env vars, Lance/Kuzu schemas, config files, and Python APIs may change without a deprecation period. Track `main` and rebuild indexes when ontology or embedding settings change.
 
 ---
@@ -124,7 +149,9 @@ If vector hits come back and graph expansion adds neighbor symbols, the install
 
 ## Wire into an MCP host
 
-### Claude Code
+> **Quick setup:** Run `java-codebase-rag install` from your Java project root. The interactive wizard handles MCP registration, skill deployment, and configuration for Claude Code, Qwen Code, and GigaCode in one step.
+
+### Claude Code (manual)
 
 With the package installed, the console script `java-codebase-rag-mcp` is on your `PATH`. Register it project-scoped:
 
@@ -207,6 +234,8 @@ Run `java-codebase-rag --help` to list grouped subcommands. Operator playbook wi
 
 | Group | Subcommand | What it does |
 |---|---|---|
+| Setup | `install` | Interactive setup wizard: config, MCP registration, skill/agent deployment, indexing. |
+| Setup | `update` | Refresh shipped artifacts (skill, agent, MCP entry) after pip upgrade. |
 | Lifecycle | `init` | First-time index. Refuses if artifacts already exist. |
 | Lifecycle | `increment` | CocoIndex catch-up + incremental Kuzu update. `--vectors-only` for Lance only. |
 | Lifecycle | `reprocess` | Full Lance + Kuzu rebuild. `--vectors-only` / `--graph-only` for a single phase. |

{java_codebase_rag-0.5.1 → java_codebase_rag-0.5.3}/README.md

@@ -44,6 +44,31 @@ pip install java-codebase-rag
 Python **3.11+** required. After install, `java-codebase-rag --help` should print the CLI groups.
 The package includes the CocoIndex lifecycle dependency used by `init`, `increment`, `reprocess`, and `erase`.
 
+### Interactive setup (recommended)
+
+Run `java-codebase-rag install` from your Java project root to launch an interactive setup wizard that:
+
+1. Detects Java source directories (Maven/Gradle modules)
+2. Configures the embedding model (auto-downloads ~90MB or uses a local path)
+3. Selects agent hosts (Claude Code, Qwen Code, GigaCode)
+4. Deploys MCP registration, skill, and agent artifacts
+5. Generates `.java-codebase-rag.yml` configuration
+6. Runs `init` to build the index
+
+```bash
+# Interactive mode
+java-codebase-rag install
+
+# Non-interactive mode (for CI/automation)
+java-codebase-rag install --non-interactive --agent claude-code
+```
+
+After `pip install --upgrade java-codebase-rag`, run `java-codebase-rag update` to refresh shipped artifacts.
+
+### Manual registration
+
+If you prefer manual configuration, see [`docs/JAVA-CODEBASE-RAG-CLI.md`](./docs/JAVA-CODEBASE-RAG-CLI.md) for the full CLI reference.
+
 > **Stability disclaimer.** This package does **not** promise backward compatibility. MCP tool contracts, env vars, Lance/Kuzu schemas, config files, and Python APIs may change without a deprecation period. Track `main` and rebuild indexes when ontology or embedding settings change.
 
 ---
@@ -84,7 +109,9 @@ If vector hits come back and graph expansion adds neighbor symbols, the install
 
 ## Wire into an MCP host
 
-### Claude Code
+> **Quick setup:** Run `java-codebase-rag install` from your Java project root. The interactive wizard handles MCP registration, skill deployment, and configuration for Claude Code, Qwen Code, and GigaCode in one step.
+
+### Claude Code (manual)
 
 With the package installed, the console script `java-codebase-rag-mcp` is on your `PATH`. Register it project-scoped:
 
@@ -167,6 +194,8 @@ Run `java-codebase-rag --help` to list grouped subcommands. Operator playbook wi
 
 | Group | Subcommand | What it does |
 |---|---|---|
+| Setup | `install` | Interactive setup wizard: config, MCP registration, skill/agent deployment, indexing. |
+| Setup | `update` | Refresh shipped artifacts (skill, agent, MCP entry) after pip upgrade. |
 | Lifecycle | `init` | First-time index. Refuses if artifacts already exist. |
 | Lifecycle | `increment` | CocoIndex catch-up + incremental Kuzu update. `--vectors-only` for Lance only. |
 | Lifecycle | `reprocess` | Full Lance + Kuzu rebuild. `--vectors-only` / `--graph-only` for a single phase. |

{java_codebase_rag-0.5.1 → java_codebase_rag-0.5.3}/build_ast_graph.py

@@ -3422,12 +3422,10 @@ def incremental_rebuild(
         pass6_match_edges(tables, verbose=verbose)
         write_kuzu(kuzu_path, tables, source_root=source_root, verbose=verbose)
 
-        n_files = _init_hash_tracker(source_root, kuzu_path)
-
         return IncrementalResult(
             mode="full_fallback",
             files_changed=0,
-            files_added=n_files,
+            files_added=0,
             files_removed=0,
             dependents_reprocessed=0,
             elapsed_sec=time.time() - t_start,
@@ -3648,12 +3646,10 @@ def _fallback_to_full(source_root: Path, kuzu_path: Path, verbose: bool, t_start
     pass6_match_edges(tables, verbose=verbose)
     write_kuzu(kuzu_path, tables, source_root=source_root, verbose=verbose)
 
-    n_files = _init_hash_tracker(source_root, kuzu_path)
-
     return IncrementalResult(
         mode="full_fallback",
         files_changed=0,
-        files_added=n_files,
+        files_added=0,
         files_removed=0,
         dependents_reprocessed=0,
         elapsed_sec=time.time() - t_start,
@@ -3785,6 +3781,7 @@ def write_kuzu(
             _verbose_stderr_line(f"[graph] writing · routes/exposes written in {time.time() - t2:.2f}s")
         _write_meta(conn, tables, source_root)
         conn.close()
+    _init_hash_tracker(source_root, db_path)
 
 
 # ---------- CLI ----------

{java_codebase_rag-0.5.1 → java_codebase_rag-0.5.3}/java_codebase_rag/pipeline.py

@@ -128,6 +128,10 @@ def run_cocoindex_update(
             stdout="",
             stderr=f"java_index_flow_lancedb.py not found under {bd}",
         )
+    # Set CocoIndex concurrency limits to prevent "too many open files" error
+    # See: https://github.com/HumanBean17/java-codebase-rag/issues/293
+    env = env.copy()
+    env.setdefault("COCOINDEX_SOURCE_MAX_INFLIGHT_ROWS", "256")
     cmd: list[str] = [str(exe), "update", COCOINDEX_TARGET]
     if full_reprocess:
         cmd.extend(["--full-reprocess", "-f"])

{java_codebase_rag-0.5.1 → java_codebase_rag-0.5.3/java_codebase_rag.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: java-codebase-rag
-Version: 0.5.1
+Version: 0.5.3
 Summary: MCP server for semantic + structural search over Java codebases
 Author: HumanBean17
 License-Expression: MIT
@@ -84,6 +84,31 @@ pip install java-codebase-rag
 Python **3.11+** required. After install, `java-codebase-rag --help` should print the CLI groups.
 The package includes the CocoIndex lifecycle dependency used by `init`, `increment`, `reprocess`, and `erase`.
 
+### Interactive setup (recommended)
+
+Run `java-codebase-rag install` from your Java project root to launch an interactive setup wizard that:
+
+1. Detects Java source directories (Maven/Gradle modules)
+2. Configures the embedding model (auto-downloads ~90MB or uses a local path)
+3. Selects agent hosts (Claude Code, Qwen Code, GigaCode)
+4. Deploys MCP registration, skill, and agent artifacts
+5. Generates `.java-codebase-rag.yml` configuration
+6. Runs `init` to build the index
+
+```bash
+# Interactive mode
+java-codebase-rag install
+
+# Non-interactive mode (for CI/automation)
+java-codebase-rag install --non-interactive --agent claude-code
+```
+
+After `pip install --upgrade java-codebase-rag`, run `java-codebase-rag update` to refresh shipped artifacts.
+
+### Manual registration
+
+If you prefer manual configuration, see [`docs/JAVA-CODEBASE-RAG-CLI.md`](./docs/JAVA-CODEBASE-RAG-CLI.md) for the full CLI reference.
+
 > **Stability disclaimer.** This package does **not** promise backward compatibility. MCP tool contracts, env vars, Lance/Kuzu schemas, config files, and Python APIs may change without a deprecation period. Track `main` and rebuild indexes when ontology or embedding settings change.
 
 ---
@@ -124,7 +149,9 @@ If vector hits come back and graph expansion adds neighbor symbols, the install
 
 ## Wire into an MCP host
 
-### Claude Code
+> **Quick setup:** Run `java-codebase-rag install` from your Java project root. The interactive wizard handles MCP registration, skill deployment, and configuration for Claude Code, Qwen Code, and GigaCode in one step.
+
+### Claude Code (manual)
 
 With the package installed, the console script `java-codebase-rag-mcp` is on your `PATH`. Register it project-scoped:
 
@@ -207,6 +234,8 @@ Run `java-codebase-rag --help` to list grouped subcommands. Operator playbook wi
 
 | Group | Subcommand | What it does |
 |---|---|---|
+| Setup | `install` | Interactive setup wizard: config, MCP registration, skill/agent deployment, indexing. |
+| Setup | `update` | Refresh shipped artifacts (skill, agent, MCP entry) after pip upgrade. |
 | Lifecycle | `init` | First-time index. Refuses if artifacts already exist. |
 | Lifecycle | `increment` | CocoIndex catch-up + incremental Kuzu update. `--vectors-only` for Lance only. |
 | Lifecycle | `reprocess` | Full Lance + Kuzu rebuild. `--vectors-only` / `--graph-only` for a single phase. |

{java_codebase_rag-0.5.1 → java_codebase_rag-0.5.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "java-codebase-rag"
-version = "0.5.1"
+version = "0.5.3"
 description = "MCP server for semantic + structural search over Java codebases"
 readme = "README.md"
 requires-python = ">=3.11"

{java_codebase_rag-0.5.1 → java_codebase_rag-0.5.3}/server.py

@@ -162,6 +162,9 @@ def _cocoindex_subprocess_env(project_root: Path) -> dict[str, str]:
     idx = os.environ.get("JAVA_CODEBASE_RAG_INDEX_DIR", "").strip()
     if idx:
         sub_env["JAVA_CODEBASE_RAG_INDEX_DIR"] = str(Path(idx).expanduser().resolve())
+    # Set CocoIndex concurrency limits to prevent "too many open files" error
+    # See: https://github.com/HumanBean17/java-codebase-rag/issues/293
+    sub_env.setdefault("COCOINDEX_SOURCE_MAX_INFLIGHT_ROWS", "256")
     return sub_env